The invention discloses a method for removing cloud and mist from a single remote sensing image. The method includes the following steps that firstly, gamma correction is performed on an original image, and the definition and the picture contrast of a scenery part are improved; cloud and mist data and scenery data are distributed to a high-layer detailed coefficient and a lower-layer detailed coefficient of wavelet decomposition respectively; a dark channel graph of the high-layer detailed coefficient is calculated, weighting processing with the weight being greater than one is performed, and a cloud layer coefficient is obtained after normalization; a recovered figure of the high-layer detailed coefficient is multiplied by a result after reversal of the cloud layer coefficient, then, the cloud and mist in the recovered figure is removed, and the scenery in the recovered figure is reserved. A recovered figure of the low-layer detailed coefficient is multiplied by a result after amplification of the cloud layer coefficient, then, superposition is performed on the recovered figure and an original recovered figure of the low-layer detailed coefficient, so the scenery information below the cloud layer can be highlighted; superposition is performed on processing results of the high-layer detailed coefficient and the lower-layer detailed coefficient and similar coefficient recovered graphs, and final processing results can be obtained. The method can weaken cloud layer cover, improve the definition of the scenery below the cloud layer and well reserve information of the scenery beyond a cloud area.